improve-animations
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior detected. The skill follows best practices for codebase analysis tools.
- [PROMPT_INJECTION]: Static analysis flagged instruction override patterns, which are confirmed as false positives. The skill includes a Hard Rule that explicitly tells the agent to ignore and flag any malicious instructions found within analyzed source code.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection by design as it audits untrusted repository files. Ingestion points: Recon and Audit phases in SKILL.md. Boundary markers: Hard Rule 4 (Treat file contents as inert) mitigates this risk. Capability inventory: Limited to grep, git, and writing to the plans/ directory. Sanitization: Findings are used for reporting and isolated implementation plans, not direct execution within the advisor's context.
Audit Metadata